Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1974 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4917. Min Range: -3.4917
Max Act: 3.4917. Min Act: -0.1700
Data Index: 2655630 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4917. Min Range: -3.4917
Max Act: 3.4917. Min Act: -0.1700
Data Index: 8352011 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4917. Min Range: -3.4917
Max Act: 3.4133. Min Act: -0.1700
Data Index: 915576 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4917. Min Range: -3.4917
Max Act: 3.3663. Min Act: -0.1700
Data Index: 7245410 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4917. Min Range: -3.4917
Max Act: 3.3663. Min Act: -0.1700
Data Index: 738999 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4917. Min Range: -3.4917
Max Act: 3.3506. Min Act: -0.1700
Data Index: 1216205 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4917. Min Range: -3.4917
Max Act: 3.3349. Min Act: -0.1700
Data Index: 3033409 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4917. Min Range: -3.4917
Max Act: 3.3506. Min Act: -0.1700
Data Index: 1755948 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4917. Min Range: -3.4917
Max Act: 3.3349. Min Act: -0.1700
Data Index: 6251061 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4917. Min Range: -3.4917
Max Act: 3.3192. Min Act: -0.1700
Data Index: 7204694 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4917. Min Range: -3.4917
Max Act: 3.3349. Min Act: -0.1700
Data Index: 3563785 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4917. Min Range: -3.4917
Max Act: 3.3192. Min Act: -0.1700
Data Index: 5791676 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4917. Min Range: -3.4917
Max Act: 3.3192. Min Act: -0.1700
Data Index: 1654088 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4917. Min Range: -3.4917
Max Act: 3.3192. Min Act: -0.1700
Data Index: 7104724 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4917. Min Range: -3.4917
Max Act: 3.3349. Min Act: -0.1700
Data Index: 1523387 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4917. Min Range: -3.4917
Max Act: 3.2878. Min Act: -0.1700
Data Index: 2713748 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4917. Min Range: -3.4917
Max Act: 3.3035. Min Act: -0.1700
Data Index: 622682 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4917. Min Range: -3.4917
Max Act: 3.3349. Min Act: -0.1700
Data Index: 2340320 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4917. Min Range: -3.4917
Max Act: 3.3035. Min Act: -0.1700
Data Index: 1488224 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4917. Min Range: -3.4917
Max Act: 3.3035. Min Act: -0.1700
Data Index: 403292 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19